The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core function involves reading and analyzing untrusted codebase content.
Ingestion points: The agent reads source files, diffs, and components using the Read, Grep, and Glob tools as defined in the 'Steps' and 'What the review must cover' sections of SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded natural language commands within the source code are provided.
Capability inventory: The skill is granted Bash, Task, and Write tools, allowing for file system modification and process execution if the agent is manipulated by instructions hidden in the code being reviewed.
Sanitization: There is no requirement or logic provided to sanitize or escape the content of the files before the agent processes them.
[COMMAND_EXECUTION]: The skill instructions specify the use of the Task tool to 'spawn a fresh read-only sub-agent' to perform independent review passes. This represents a form of dynamic task generation and execution.

frontend-review